This paper describes an attempt to make use of machine learning or self-organizing processes in the design of a pattern-recognition program. The program starts not only without any knowledge of specific patterns to be input, but also without any operators for processing inputs. Operators are generated and refined by the program itself as a function of the problem space and of its own successes and failures in dealing with the problem space. Not only does the program learn information about different patterns, it also learns or constructs, in part at least, a secondary code appropriate for the analysis of the particular set of patterns input to it.

The purpose of this report is to describe in detail an informationProcessing model of elementary human symbolic learning processes. Thismodel is realized by a computer program called the Elementary Perceiverand Memorizer (EPAM).The EPAM program is the precise statement of an information processingtheory of verbal learning that provides an alternative to other verballearning theories which have been proposed.1 It is the result of an attemptto state quite precisely a parsimonious and plausible mechanism sufficientto account for the rote learning of nonsense syllables. The criticalevaluation of EPAM must ultimately depend not upon the interest whichit may have as a learning machine, but upon its ability to explain andPredict the phenomena of verbal learning. Proceedings of the Western Joint Computer Conference, 1961, 19:121-132. Reprinted in Feigenbaum & Feldman, Computers and Thought (1963).

Artificial intelligence project memo 30, Massachusetts Institute of Technology.

This article is concerned with the psychology of human thinking. It setsforth a theory to explain how some humans try to solve some simpleformal problems. The research from which the theory emerged is intimatelyrelated to the field of information processing and the construction of intelligentautomata, and the theory is expressed in the form of a computerprogram. The rapid technical advances in the art of programming digitalcomputers to do sophisticated tasks have made such a theory feasible.It is often argued that a careful line must be drawn between the attemptto accomplish with machines the same tasks that humans perform, andthe attempt to simulate the processes humans actually use to accomplishthese tasks. The program discussed in the report, GPS (General ProblemSolver), maximally confuses the two approaches—with-mutual"!benefit. Lerende Automaten, Munich: Oldenberg KG

in Proceedings of the Western Joint Computer Conference 1961, pp. 215-218.

Journal of the ACM, Vol. 7, No. 3, pp. 201-215

CACM, 7, 219–244.

In von Foerster, H. (ed) Illinois Symposium on Principles of Self-Organization, Univ. of Illinois, Urbana, IL (1960)

in Advances in Computers [F. Alt, ed.], New York: Academic

This is an attempt to analyze attitudes and arguments brought forth by questions like "Can machines think?" and "Can machines exhibit intelligence?" Its purpose is to improve the climate which surrounds research in the field of machine or artificial intelligence. Its goal is not to convince those who answer the above questions negatively that they are wrong (although an attempt will be made to refute some of the negative arguments) but that they should be tolerant of research investigating these questions. The negative attitudes existent today tend to inhibit such research.Reprinted in Feigenbaum & Feldman, Computers and Thought (1963).Also in Datamation 9(3), March 1963, pp.34-38.Symposium on Bionics, Rand Technical Report 60 600, pp. 13-19